selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-21 12:49:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

gpu self hosted setup guide (no-mistakes)

Browse Source
This commit is contained in:
Igor Loskutov
2025-12-09 11:25:09 -05:00
parent 5779478d3c
commit 2b3f28993f
14 changed files with 799 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
gpu/modal_deployments/reflector_diarizer.py
View File

@@ -24,6 +24,12 @@ app = modal.App(name="reflector-diarizer")
upload_volume = modal.Volume.from_name("diarizer-uploads", create_if_missing=True)
# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
# If you modify the audio format detection logic, you MUST update all copies:
# - gpu/self_hosted/app/utils.py
# - gpu/modal_deployments/reflector_transcriber.py (2 copies)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/modal_deployments/reflector_diarizer.py (this file)
def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
parsed_url = urlparse(url)
url_path = parsed_url.path
@@ -39,6 +45,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
return AudioFileExtension("wav")
if "audio/mp4" in content_type:
return AudioFileExtension("mp4")
if "audio/webm" in content_type or "video/webm" in content_type:
return AudioFileExtension("webm")
raise ValueError(
f"Unsupported audio format for URL: {url}. "

25
gpu/modal_deployments/reflector_transcriber.py
View File

@@ -99,6 +99,12 @@ image = (
)
# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
# If you modify the audio format detection logic, you MUST update all copies:
# - gpu/self_hosted/app/utils.py
# - gpu/modal_deployments/reflector_transcriber.py (this file - 2 copies!)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/modal_deployments/reflector_diarizer.py
def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
parsed_url = urlparse(url)
url_path = parsed_url.path
@@ -114,6 +120,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
return AudioFileExtension("wav")
if "audio/mp4" in content_type:
return AudioFileExtension("mp4")
if "audio/webm" in content_type or "video/webm" in content_type:
return AudioFileExtension("webm")
raise ValueError(
f"Unsupported audio format for URL: {url}. "
@@ -316,6 +324,11 @@ class TranscriberWhisperFile:
import numpy as np
from silero_vad import VADIterator
# IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
# If you modify this function, you MUST update all copies:
# - gpu/modal_deployments/reflector_transcriber.py (this file)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/self_hosted/app/services/transcriber.py
def vad_segments(
audio_array,
sample_rate: int = SAMPLERATE,
@@ -323,6 +336,7 @@ class TranscriberWhisperFile:
) -> Generator[TimeSegment, None, None]:
"""Generate speech segments as TimeSegment using Silero VAD."""
iterator = VADIterator(self.vad_model, sampling_rate=sample_rate)
audio_duration = len(audio_array) / float(SAMPLERATE)
start = None
for i in range(0, len(audio_array), window_size):
chunk = audio_array[i : i + window_size]
@@ -342,6 +356,9 @@ class TranscriberWhisperFile:
start / float(SAMPLERATE), end / float(SAMPLERATE)
)
start = None
# Handle case where audio ends while speech is still active
if start is not None:
yield TimeSegment(start / float(SAMPLERATE), audio_duration)
iterator.reset_states()
upload_volume.reload()
@@ -407,6 +424,12 @@ class TranscriberWhisperFile:
return {"text": " ".join(all_text), "words": all_words}
# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
# If you modify the audio format detection logic, you MUST update all copies:
# - gpu/self_hosted/app/utils.py
# - gpu/modal_deployments/reflector_transcriber.py (this file - 2 copies!)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py
# - gpu/modal_deployments/reflector_diarizer.py
def detect_audio_format(url: str, headers: dict) -> str:
from urllib.parse import urlparse
@@ -424,6 +447,8 @@ def detect_audio_format(url: str, headers: dict) -> str:
return "wav"
if "audio/mp4" in content_type:
return "mp4"
if "audio/webm" in content_type or "video/webm" in content_type:
return "webm"
raise HTTPException(
status_code=400,

13
gpu/modal_deployments/reflector_transcriber_parakeet.py
View File

@@ -90,6 +90,12 @@ image = (
)
# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
# If you modify the audio format detection logic, you MUST update all copies:
# - gpu/self_hosted/app/utils.py
# - gpu/modal_deployments/reflector_transcriber.py (2 copies)
# - gpu/modal_deployments/reflector_transcriber_parakeet.py (this file)
# - gpu/modal_deployments/reflector_diarizer.py
def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
parsed_url = urlparse(url)
url_path = parsed_url.path
@@ -105,6 +111,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
return AudioFileExtension("wav")
if "audio/mp4" in content_type:
return AudioFileExtension("mp4")
if "audio/webm" in content_type or "video/webm" in content_type:
return AudioFileExtension("webm")
raise ValueError(
f"Unsupported audio format for URL: {url}. "
@@ -301,6 +309,11 @@ class TranscriberParakeetFile:
audio_array, sample_rate = librosa.load(file_path, sr=SAMPLERATE, mono=True)
return audio_array
# IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
# If you modify this function, you MUST update all copies:
# - gpu/modal_deployments/reflector_transcriber.py
# - gpu/modal_deployments/reflector_transcriber_parakeet.py (this file)
# - gpu/self_hosted/app/services/transcriber.py
def vad_segment_generator(
audio_array,
) -> Generator[TimeSegment, None, None]: